← Back to all development cases
This case was judged by an anonymized AI reviewer and has not been independently reviewed by people; inspect the draft, cards, and both outputs to assess it.
AutocompleteWith cards better191 / 280 · beu-98549154eac65eb2

The halo model for cosmology: a pedagogical review

Astrophysics · 2303.08752v2

FLOWING EVIDENCE BENCHMARK

How do we compare writing with and without cards?

At the same writing position, the same model produces one first result with cards and one without. All 280 pairs enter the overall anonymized review, which assesses whether a decision not to continue fits the draft.

Overall: 138 with-card wins, 26 ties, 107 no-card wins, 5 pairs where neither was usable, and 4 inconclusive judgments. Both sides wrote text in 218 pairs; 48 had a deliberate stop and 14 included an invalid output.

SAME DRAFT · WITH OR WITHOUT CARDS

01 · FIXED WRITING POSITION

MANUSCRIPT

Same writing position ▌

Matched autocomplete at the same draft position

02 · TWO MATCHED VERSIONS

SHARED BY BOTH

Draft, writing task, and generation model

A · With cards

Relevant literature cards supplied

B · Without cards

No literature cards supplied

Generation model

Same model and version

A → first output

B → first output

Anonymized AI judge

First outputs are anonymized as X and Y

Continuation review: accuracy, fit to the writing task and usability
Returns: X preferred / tie / Y preferred / both unusable

Review again with the answer order swapped

HOW DOES BLIND JUDGING WORK?

① Anonymize both outputs
The AI judge sees the same draft and both first outputs without knowing which received cards.

② Compare and swap order
The judge applies task-specific criteria in X/Y and then Y/X order.

③ Review disagreements
A third pass resolves disagreements. Incomplete reviews remain in the denominator.

How are positions and cards selected?

We selected 40 writing positions in each of seven fields, for 280 comparisons. The position and relevant literature cards were set before each comparison, so both versions began from the same draft.

The main result retains every frozen position, including places where cards might not add a useful next move. This avoids selecting cases based on their outputs, but 49% describes the whole cohort, not a win rate where evidence clearly had an opportunity to help. This cohort did not record that opportunity label for each position before generation, so those two groups cannot yet be separated reliably.

CARD USE · 140/280

Reported card use in continuations with text

The model reports whether a card affected its continuation. In 140 of 280 tests it produced continuation text and reported card use. The previous count of 150 included 10 cases without continuation text and has been corrected.

COMPARISON · 70 / 7 / 30

Which written version was better?

Of the 107 reported-use cases where both versions produced text, the blinded AI judge preferred the with-card version 70 times, found 7 about the same, and preferred the without-card version 30 times.

How are the two table percentages calculated?

ADOPTION COVERAGE

140reported use with text
÷
280all positions
=
50%

WITH-CARD VERSION PREFERRED

70with cards better
÷
107comparable tests
=
65%

The percentages use different groups: 50% counts continuations with text reporting card use among all 280 tests; 65% covers the 107 such cases with text on both sides. The generating model reports card use, while an anonymized AI judge compares writing quality.

Card use is self-reported by the generator. The anonymized AI judge sees the draft and source snippets, so source-aware preference remains possible; there was no independent human review. The overall result describes these 280 frozen positions, not a win probability for any writing task.

Manuscript writing position

Text excerpt · not a PDF page

Research manuscript · excerpt

The halo model for cosmology: a pedagogical review

1 Introduction

…lapse in exotic cosmologies, the halo model also provides predictions for non-linear clustering in beyond- Λ \Lambda CDM models. The halo model has been widely used to model observations of a variety of large-scale structure probes, most notably as the primary technique to model the underlying non-linear matter power spectrum. By documenting these varied and often distinct use cases, we seek to further coherent halo model analyses of future multi-tracer observables. This review is accompanied by the release of pyhalomodel , flexible software to conduct a wide range of halo-model calculations.

↓ Next paragraph was generated here

The highlighted text is near the writing position. This is a layout of the evaluation input, not a PDF screenshot.

A matched comparison at the same writing positionOverall AI review: With cards better

Both arms use the same model, task and manuscript context. Only the retrieved passages differ. The first recorded output from each arm is shown below.

Read overall AI review rationale

A = without cards · B = with cards

The draft ends with two sentences establishing the paper's purpose and introducing pyhalomodel software. This is a classic introduction-to-body transition point in academic writing. Output A abstains with 'complete', but the manuscript clearly needs a next move: either a roadmap of paper structure or a transition to technical content. Ending here would leave the reader without guidance on what follows. Output B provides a standard, well-scoped roadmap paragraph ('The review is organised as follows...') that naturally follows the introduction of purpose and software. It fits the genre conventions of review papers, maintains appropriate scope, and requires no repair to insert. The paragraph is coherent, accurate in its generic structure, and directly serves reader utility by previewing content. Output A's abstention is not appropriate because the draft has not yet made a complete move—the introduction lacks structural signposting that would make it self-contained.

Evidence

Same model and position · retrieved passages supplied · first output

Preferred by blind review

The review is organised as follows. Section 2 introduces the halo model formalism, Section 3 surveys its applications to cosmological observables, and Section 4 discusses extensions beyond the standard framework.

Passages supplied to the Evidence version

Card 1 · Nonlinear cosmological matter power spectrum with massive neutrinos: The halo model

Measurements of the linear power spectrum of galaxies have placed tight constraints on neutrino masses. We extend the framework of the halo model of cosmological nonlinear matter clustering to include the effect of massive neutrino infall into cold dark matter (CDM) halos. The magnitude of the effec…

Read full passage excerpt

Measurements of the linear power spectrum of galaxies have placed tight constraints on neutrino masses. We extend the framework of the halo model of cosmological nonlinear matter clustering to include the effect of massive neutrino infall into cold dark matter (CDM) halos. The magnitude of the effect of neutrino clustering for three degenerate mass neutrinos with ${m}_{{\ensuremath{\nu}}_{i}}=0.9\text{ }\mathrm{e}\mathrm{V}$ is of order $\ensuremath{\sim}1%$, within the potential sensitivity of upcoming weak lensing surveys. In order to use these measurements to further constrain---or eventually detect---neutrino masses, accurate theoretical predictions of the nonlinear power spectrum in the presence of massive neutrinos will be needed, likely only possible through high-resolution multiple particle (neutrino, CDM and baryon) simulations.

Card 2 · Improved mixed dark matter halo model for ultralight axions

We present a complete halo model for mixed dark matter composed of cold dark matter (CDM) and ultralight axionlike particles (ULAs). Our model treats ULAs as a biased tracer of CDM, in analogy to treatments of massive neutrinos and neutral hydrogen. The model accounts for clustering of ULAs around C…

Read full passage excerpt

We present a complete halo model for mixed dark matter composed of cold dark matter (CDM) and ultralight axionlike particles (ULAs). Our model treats ULAs as a biased tracer of CDM, in analogy to treatments of massive neutrinos and neutral hydrogen. The model accounts for clustering of ULAs around CDM host halos, and fully models the cross correlations of both components. The model inputs include the ULA Jeans scale, and soliton density profile. Our model can be used to predict the matter power spectrum, $P(k)$, on nonlinear scales for subpopulations of ULAs across the mass range ${10}^{\ensuremath{-}33}\text{ }\text{ }\mathrm{eV}\ensuremath{\le}m\ensuremath{\le}{10}^{\ensuremath{-}21}\text{ }\mathrm{eV}$, and can be calibrated against future mixed DM simulations to improve its accuracy. The mixed DM halo model also allows us to assess the importance of various approximations.

Card 3 · Effects of Baryons and Dissipation on the Matter Power Spectrum

We study the importance of baryonic physics on predictions of the matter power spectrum as it is relevant for forthcoming weak-lensing surveys. We quantify the impact of baryonic physics using a set of cosmological numerical simulations. Each simulation has the same initial density field, but models…

Read full passage excerpt

We study the importance of baryonic physics on predictions of the matter power spectrum as it is relevant for forthcoming weak-lensing surveys. We quantify the impact of baryonic physics using a set of cosmological numerical simulations. Each simulation has the same initial density field, but models a different set of physical processes. We find that baryonic processes significantly alter predictions for the matter power spectrum relative to models that include only gravitational interactions. Our results imply that future weak-lensing experiments such as LSST and SNAP will likely be sensitive to the uncertain physics governing the nonlinear evolution of the baryonic component of the universe if these experiments are primarily limited by statistical uncertainties. In particular, this effect could be important for forecasts of the constraining power of future surveys if information from scales l ≳ 1000 is included in the analysis. We find that deviations are caused primarily by the rear …

Card 4 · Halo concentration and the dark matter power spectrum

We explore the connection between halo concentration and the dark matter power spectrum using the halo model. We fit halo model parameters to non-linear power spectra over a large range of cosmological models. We find that the non-linear evolution of the power spectrum generically prefers the concen…

Read full passage excerpt

We explore the connection between halo concentration and the dark matter power spectrum using the halo model. We fit halo model parameters to non-linear power spectra over a large range of cosmological models. We find that the non-linear evolution of the power spectrum generically prefers the concentration at non-linear mass scale to decrease with the effective slope of the linear power spectrum, in agreement with the direct analysis of the halo structure in different cosmological models. Using these analyses, we compute the predictions for the non-linear power spectrum beyond the current resolution of N-body simulations. We find that the halo model predictions are generically below the analytical non-linear models, suggesting that the latter may overestimate the amount of power on small scales.

Card 5 · Halo model description of the non-linear dark matter power spectrum at k≫ 1 Mpc−1

Accurate knowledge of the non-linear dark-matter power spectrum is important for understanding the large-scale structure of the Universe, the statistics of dark-matter haloes and their evolution, and cosmological gravitational lensing. We analytically model the dark-matter power spectrum and its cro…

Read full passage excerpt

Accurate knowledge of the non-linear dark-matter power spectrum is important for understanding the large-scale structure of the Universe, the statistics of dark-matter haloes and their evolution, and cosmological gravitational lensing. We analytically model the dark-matter power spectrum and its cross-power spectrum with dark-matter haloes. Our model extends the halo-model formalism, including realistic substructure population within individual dark-matter haloes and the scatter of the concentration parameter at fixed halo mass. We consider three prescriptions for the mass-concentration relation and two for the substructure distribution in dark-matter haloes. We show that this extension of the halo model mainly increases the predicted power on the small scales, and is crucial for proper modeling the cosmological weak-lensing signal due to low-mass haloes. Our extended formalism shows how the halo model approach can be improved in accuracy as one increases the number of ingredients that …

Model-reported card use

The model did not report that any card materially affected this completion.

No Evidence

Same model and position · no retrieved passages · first output

Not preferred in this comparison

No continuation text was produced.

Model action:complete

Earlier card-use comparison

The earlier diagnostic compared only cases with reported card use and text on both sides; its scope differs from the overall AI review above.

This case does not have both with-card continuation text and a model-reported use record. It remains among all 280 tests but does not enter the reported-use comparison.

The passages are input material; their presence does not mean an output used them or that they support every claim. Draft and source passages are excerpted; no simulated scores or PDF appear here.